Department of Orthopaedic Surgery, Center for Hip Preservation, Orthopaedic and Rheumatologic Institute, Institute Cleveland Clinic Foundation, Mail code A41, 9500 Euclid Ave, Cleveland, OH, 44195, USA.
Eur J Orthop Surg Traumatol. 2024 Dec;34(8):3809-3825. doi: 10.1007/s00590-024-04076-5. Epub 2024 Aug 30.
Machine learning (ML) models may offer a novel solution to reducing postoperative complication rates and improving post-surgical outcomes after total joint arthroplasty (TJA). However, the variety of different ML models that exist paired with the increasing number of potential inputs can make the implementation of this tool challenging. Therefore, we conducted a systematic review to assess the most optimal inputs of different ML models in predicting postoperative (1) medical outcomes, (2) orthopedic outcomes, and (3) patient-reported outcome measures (PROMs) after total joint arthroplasty.
The PubMed, MEDLINE, EBSCOhost, and Google Scholar databases were utilized to identify all studies evaluating ML models predicting outcomes following TJA between January 1, 2000, and June 23, 2023 (PROSPERO study protocol registration: CRD42023437586). The mean risk of bias in non-randomized studies-of interventions score, was 13.8 ± 0.5. Our initial query yielded 656 articles, of which 25 articles aligned with our aims, examining over 20 machine learning models and 1,555,300 surgeries. The area under the curve (AUC), accuracy, inputs, and the importance of each input were reported.
Twelve studies evaluating medical complications with 13 ML models reported AUCs ranging from 0.57 to 0.997 and accuracy between 88% and 99.98%. Key predictors included age, hyper-coagulopathy, total number of diagnoses, admission month, and malnutrition. Five studies evaluating orthopedic complications with 10 ML models reported AUCs from 0.49 to 0.93 and accuracy ranging from 92 to 97%, with age, BMI, CCI, AKSS scores, and height identified as key predictors. Ten studies evaluating PROMs comprising of 12 different ML models had an AUC ranging from 0.453 to 0.97 ranked preoperative PROMs as the post-predictive input. Overall, age was the most predictive risk factor for complications post-total joint arthroplasty (TJA).
These studies demonstrate the predictive capabilities of these models for anticipating complications and outcomes. Furthermore, these studies also highlight ML models' ability to identify non-classical variables not commonly considered in addition to confirming variables known to be crucial. To advance the field, forthcoming research should adhere to established guidelines for model development and training, employ industry-standard input parameters, and subject their models to external validity assessments.
机器学习 (ML) 模型可能为降低全关节置换术 (TJA) 后术后并发症发生率和改善术后结果提供一种新的解决方案。然而，现有的各种不同的 ML 模型以及越来越多的潜在输入，使得该工具的实施具有挑战性。因此，我们进行了一项系统评价，以评估不同 ML 模型在预测术后 (1) 医疗结果、(2) 骨科结果和 (3) 患者报告的结果测量 (PROM) 方面的最佳输入。
使用 PubMed、MEDLINE、EBSCOhost 和 Google Scholar 数据库，检索 2000 年 1 月 1 日至 2023 年 6 月 23 日期间评估 ML 模型预测 TJA 后结果的所有研究（PROSPERO 研究方案注册：CRD42023437586）。非随机干预研究的平均偏倚风险评分（mean risk of bias in non-randomized studies-of-interventions score）为 13.8±0.5。我们最初的查询产生了 656 篇文章，其中 25 篇文章符合我们的目标，研究了 20 多个机器学习模型和 1555300 例手术。报告了曲线下面积 (AUC)、准确性、输入以及每个输入的重要性。
12 项评估医疗并发症的研究（涉及 13 个 ML 模型）报告的 AUC 范围为 0.57 至 0.997，准确性范围为 88%至 99.98%。关键预测因素包括年龄、高凝状态、总诊断数、入院月份和营养不良。5 项评估骨科并发症的研究（涉及 10 个 ML 模型）报告的 AUC 范围为 0.49 至 0.93，准确性范围为 92%至 97%，年龄、BMI、CCI、AKSS 评分和身高被确定为关键预测因素。10 项评估包含 12 个不同 ML 模型的 PROMs 的研究的 AUC 范围为 0.453 至 0.97，将术前 PROMs 列为预测后的输入。总体而言，年龄是 TJA 后并发症的最具预测性的危险因素。
这些研究表明这些模型具有预测并发症和结果的能力。此外，这些研究还强调了 ML 模型识别非经典变量的能力，这些变量除了确认已知至关重要的变量外，通常不会被考虑。为了推动该领域的发展，未来的研究应遵守模型开发和培训的既定准则，采用行业标准的输入参数，并对其模型进行外部有效性评估。
